Senior Specialist, AI Evals Engineer
MSD (Merck & Co., Inc.) (company site, opens in a new tab)7–11 yrsHyderabadHybridDirect career pageEst. 35–60 LPA
Posted 6d ago
Reach people at MSD (Merck & Co., Inc.)
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at MSD (Merck & Co., Inc.) you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Own end-to-end evaluation strategy and delivery for AI systems, including foundation/fine-tuned models, RAG pipelines and agents; assess quality, robustness and safety.
- Build reusable evaluation datasets, metrics, scoring rubrics and production pipelines, validating automated and LLM-as-a-judge methods against human judgment.
- Diagnose failure modes and advise release decisions; align standards with engineering, product and risk teams, while providing technical leadership and mentorship.
Minimum Requirements
- Work Experience Required: 7–11 years in AI/ML evaluations, testing and benchmarking; the JD also specifies 6+ years on AI/ML projects, including substantial hands-on experience designing and leading system evaluations.
- Bachelor’s or Master’s degree in Computer Science, AI/ML, Data Science, Engineering, or a related science or technology discipline.
- Strong Python development experience, including scientific computing and production-grade evaluation tooling; hands-on expertise across evaluation approaches for models, RAG and agents, including safety testing.
- Role is based in Hyderabad with a hybrid arrangement; visa sponsorship is not available.
Ideal Candidate Profile
- Has led evaluations across model, RAG and agent systems and can choose suitable benchmarks, human review, LLM-as-a-judge, task-completion or safety methods for each use case.
- Can turn evaluation evidence into clear failure analyses, acceptance criteria and release recommendations for engineering teams and senior stakeholders.
- Brings technical direction and mentoring experience across cross-functional AI projects; pharmaceutical domain exposure, cloud experience and evaluation-platform familiarity are advantageous, not stated as mandatory.