---
title: 'Research Engineer, AI Evaluations at Karya'
canonical: 'https://feeny.ai/job/research-engineer-ai-evaluations-karya-bengaluru-madk4mr4hq2s'
type: 'job'
last_seen: '2026-10-27'
---

# Research Engineer, AI Evaluations at Karya

- **Company:** Karya
- **Location:** Bengaluru, India
- **Posted:** 2026-10-21
- **Last confirmed live:** 2026-10-27
- **Apply:** https://job-boards.greenhouse.io/karya/jobs/5459428008

## Job description

Karya’s mission is to leverage the AI revolution to create dignified earning and learning opportunities for low-income communities across the world. In India, our smartphone-based digital work platform has enabled over 120,000 people to build language datasets and evaluate AI models while earning fair wages. With pilots in Kenya and Ethiopia and partnerships with leading AI labs, we are advancing language technologies for underrepresented communities. By combining dignified digital work with frontier AI innovation, Karya hopes to build a new AI economy that is equitable, inclusive, and community driven.

Karya's AI Evaluations team measures how well AI models serve people in the languages and contexts global benchmarks miss. We work with partners including Anthropic and Microsoft Research, alongside government and civil society, running evaluations on our own platform with native speakers and domain experts across India and beyond. Our benchmarks, leaderboards and reports aim to help model developers and decision-makers understand where models work well and where they fall short.

As a Research Engineer, you will design, build and run these evaluations end to end, across eval design, model deployment, statistical analysis and engineering. The work spans ASR, TTS, machine translation and chat, with newer frontiers in agentic and multimodal evaluation.

## What We Do

- Benchmark design: curating representative query sets and defining rubrics that score reliably and separate models meaningfully.
- Expert input: designing elicitation and adjudication processes that turn domain expertise into consistent, scalable judgments.
- Bias evaluation: developing methods to detect gender and other social biases in LLM outputs across languages and cultures.
- Error attribution: tracing failures in multi-stage AI pipelines to the responsible component.
- Leaderboards: aggregating noisy human and automated judgments into rankings that account for annotator reliability and uncertainty.

## Key Responsibilities

- Design benchmarks, rubrics and metrics, and choose between human, automated and hybrid evaluation based on reliability, cost and validity trade-offs.
- Deploy and serve models through APIs and self-hosted GPU inference, with versioned configs, logging and controls for reproducible results at scale.
- Analyse evaluation data with sound statistical methods (agreement, uncertainty, significance, disaggregation), and validate automated judges against human ground truth.
- Build and maintain modular evaluation pipelines and leaderboard infrastructure, covering sampling, inference, task packaging, scoring and reporting, with tested, documented code.
- Prototype new evaluation methods, and turn results into publications, technical reports and public releases.

## Who You Are

- 4+ years in ML engineering or applied ML research, shipping production-quality systems.
- Strong software engineering, including clean, tested Python and end-to-end data and ML pipelines.
- Deep working knowledge of modern AI architectures and inference, including quality, latency and cost trade-offs.
- Rigorous grounding in probability and statistics on noisy real-world data.
- Ability to independently turn ambiguous questions into rigorous, executable technical work.
- Master's degree in Computer Science, Machine Learning, NLP or a related field preferred; equivalent industry or research experience will be considered.

Strong differentiators

- Experience building benchmarks or evaluation systems.
- Experience with human judgment data.
- Experience with speech or multilingual NLP, especially Indian languages.
- Publications or open-source work in AI or related domains.

Mindset

- Sceptical of numbers until you know how they were produced.
- Thrives in interdisciplinary teams spanning engineering, research, social science, operations and domain experts.
- Comfortable with ambiguity, messy data and evolving requirements, and maintains rigour under tight timelines.
- Cares about building AI that works for the people it is meant to serve.

## What We Offer

- Flexible leave and vacation policy
- Hybrid work options
- Insurance as per industry standards
- Access to leaders in technology and social impact sectors
- A chance to contribute meaningfully to AI, digital equity, and rural development

Karya celebrates diversity and is an equal opportunity employer. All applicants will be considered without regard to race, religion, gender identity, sexual orientation, disability, or any other protected status.

## About Karya

## Core Business
- **Primary industry/industries**: AI Data Services, Language Technology, Ethical Data Collection, Impact Tech
- **Target customers**: B2B – AI labs (e.g., Google DeepMind, Microsoft), enterprises building multilingual AI systems, government and public-sector AI initiatives
- **Mission**: “Create dignified digital work that improves livelihoods while shaping AI systems that reflect the people who build them.” [karya.in](https://www.karya.in/about/mission/)

## Products & Services
- **Conversational Speech Datasets**: Large-scale datasets across 22 official Indian languages for speech recognition and conversational AI. [karya.in](https://www.karya.in/)
- **Evaluation Benchmarks (Samiksha)**: National-scale evaluation frameworks covering 6 Indian languages, 17 models, and 4 key domains (healthcare, agriculture, finance, law, education, public services). [karya.in](https://www.karya.in/)
- **Data Collection & Annotation Services**: Domain-specific transcription, localized translation, and multimodal dataset creation (including egocentric datasets for physical/embodied AI). [karya.in](https://www.karya.in/)
- **Karya Platform (PaaS)**: A digital work platform that distributes AI-data microtasks to rural workers, enabling human-in-the-loop evaluation and bias mitigation. [karya.in](https://www.karya.in/) and [linkedin.com](https://in.linkedin.com/company/karya-inc)

## Market Standing
- **Valuation/Market Cap**: Not disclosed (private company)
- **Total Funding**: USD $1,000,000 (grant from Google.org, led by Google.org, November 2024) [linkedin.com](https://in.linkedin.com/company/karya-inc)
- **Key Metric**: Over 130,000 workers have completed 65+ million paid digital tasks; 99 employees (45.8% YoY growth) [linkedin.com](https://in.linkedin.com/company/karya-inc)
- **Notable Investors/Partners**: Google.org (grant), Google DeepMind, Microsoft, partnerships with leading AI labs; expanded to Kenya and Ethiopia [karya.in](https://www.karya.in/about/mission/)
- **Growth Signals**: Launched Karya Institute (2025) to explore the future of work in AI; published research at CHI 2019 and LREC 2020; spun out of Microsoft Research; presented to Satya Nadella and Sundar Pichai [karya.in](https://www.karya.in/about/mission/)

## Competitive Advantages
- **Ethical & Inclusive Data Sourcing**: Karya’s platform directly benefits low-income rural workers by paying fair wages, differentiating itself from exploitative data labeling models.
- **Deep Focus on Underrepresented Languages**: Specializes in 22 Indian languages and underserved communities globally, creating datasets that major AI companies cannot easily replicate.
- **End-to-End Pipeline**: Offers data collection, annotation, evaluation, and deployment – a vertically integrated stack for multilingual AI.
- **Research-Backed Origin**: Born from Microsoft Research, giving it credibility and technical depth in crowdsourced work and language technology.

## Strategic Focus
- **Geographic Expansion**: Pilots in Kenya and Ethiopia to replicate the model for African languages and communities.
- **“Earn & Learn” Strategy**: Developing pathways for workers to gain skills and move out of poverty, combining earning with upskilling.
- **Karya Institute**: Research arm exploring the future of digital work and AI’s impact on low-income communities.
- **Product Diversification**: Moving beyond data collection into evaluation benchmarks and platform-as-a-service for enterprise clients.

## Why Work Here
- **Mission-Driven Culture**: Join a team committed to using AI for social impact – creating dignified work and inclusive AI systems.
- **Growth Trajectory**: Rapidly scaling (45% headcount growth YoY) with opportunities to shape operations, technology, and impact in India and Africa.
- **Work Policy**: Mix of office (Bangalore) and remote roles (e.g., Visual & Motion Designer Remote, Health Program Lead Remote) as seen on the careers page. [greenhouse.io](http://job-boards.greenhouse.io/karya)
- **Engineering & Research Focus**: Strong technical team (29% in technical roles) with backgrounds from Microsoft, Wadhwani AI, and top Indian institutes. Work on cutting-edge NLP, speech, and multimodal AI.
- **Notable Perks**: The chance to work directly with global AI labs (Google DeepMind, Microsoft) and present to top tech leaders. Limited employer reviews (2.0/5.0 from 1 review on LinkedIn) – candidate should research culture further.

## Sources
1. [karya.in – Homepage](https://www.karya.in/)
2. [karya.in – About/Mission](https://www.karya.in/about/mission/)
3. [LinkedIn – Karya Company Page](https://in.linkedin.com/company/karya-inc)
4. [Greenhouse – Karya Careers Page](http://job-boards.greenhouse.io/karya)

## Other roles at Karya

- [Founder's Associate](https://feeny.ai/job/founder-s-associate-karya-bengaluru-yc0bmhewcjqf) — Bengaluru, India
- [Partnerships Associate](https://feeny.ai/job/partnerships-associate-karya-bengaluru-h9jx4pf9r3ft) — Bengaluru, India
- [Senior Backend Engineer](https://feeny.ai/job/senior-backend-engineer-karya-bengaluru-kb0c1yxzz1q5) — Bengaluru, India
- [Data Engineer](https://feeny.ai/job/data-engineer-karya-bengaluru-248ehwkbew69) — Bengaluru, India
- [Research Intern - AI Evaluations](https://feeny.ai/job/research-intern-ai-evaluations-karya-bengaluru-vhhwvkayktkt) — Bengaluru, India
- [Strategy & Operations Analyst](https://feeny.ai/job/strategy-operations-analyst-karya-bengaluru-gxfb4pddyzek) — Bengaluru, India
- [Technical Support & Solutions Associate - Platform-as-a-Service (PaaS)](https://feeny.ai/job/technical-support-solutions-associate-platform-as-a-service-paas-karya-bengaluru-4yrfyjr0ffxz) — Bengaluru, India
- [Lead - Public Policy](https://feeny.ai/job/lead-public-policy-karya-delhi-m0xke4tbwmpv) — Delhi, India
- [Community Coordinator - Work Management](https://feeny.ai/job/community-coordinator-work-management-karya-bengaluru-karnataka-india-delhi-x93npdqsjye0) — Bengaluru Karnataka India Delhi, India
- [Associate - Impact Program](https://feeny.ai/job/associate-impact-program-karya-bengaluru-karnataka-india-delhi-pm5qfxt5607p) — Bengaluru Karnataka India Delhi, India