AI Engineer
Opella
full-time
Posted on:
Location Type: Office
Location: Hyderabad • India
Visit company websiteExplore more
About the role
- Design and optimize prompts, system messages, domain instructions, and task-agent workflows to maximize accuracy, reliability, and interpretability.
- Build and maintain RAG pipelines including domain retrieval services, embeddings-based matching, similarity search, and knowledge extraction frameworks.
- Implement LLM model refinement using fine-tuning, prompt tuning, or domain corpus training where needed.
- Develop low-latency inference APIs and microservices using Python, FastAPI, Docker, and cloud execution environments.
- Improve performance through token budgeting, context compression, vector indexing, and cost-aware inference scaling.
- Build automated evaluation harnesses and hallucination prevention frameworks, including guardrails for enterprise AI usage.
- Collaborate with platform & security teams to ensure privacy-safe, secure, and compliant use of AI in production.
- Monitor model drift, usage patterns, and failure modes, driving continuous improvement in precision and reliability.
- Align AI outputs with governed KPIs and semantic standards, in collaboration with enterprise data architects.
Requirements
- 7+ years of hands-on experience in AI/ML engineering building production-ready systems.
- Strong programming ability in Python, with deployment experience using FastAPI, Flask, or similar frameworks.
- Practical expertise with LLMs, embeddings, RAG workflows, and vector search technologies (e.g., Pinecone, Elastic Vectors).
- Solid grounding in machine learning fundamentals, including model training, fine-tuning, evaluation, and inference optimization.
- Experience building scalable inference pipelines, leveraging Docker, Kubernetes, Lambda, or serverless compute frameworks.
- Familiarity with ML lifecycle practices — monitoring, drift detection, versioning, reproducibility, and performance tuning (MLFlow, Airflow, etc).
- Ability to build clean, reliable software, including CI/CD workflows, version control, automated testing, and secure deployment practices.
- Working knowledge of statistics, feature engineering, and domain interpretation, ideally within commercial, retail, CPG, or data-intensive environments.
- Understanding of semantic models, governed KPIs, metadata alignment, and SQL-based analytics integration (Snowflake/DBT is a plus).
Benefits
- Health benefits
- Professional development opportunities
Applicant Tracking System Keywords
Tip: use these terms in your resume and cover letter to boost ATS matches.
Hard skills
PythonFastAPIFlaskLLMsembeddingsRAG workflowsvector searchmodel trainingfine-tuninginference optimization
Soft skills
collaborationcontinuous improvementproblem-solvingcommunicationreliabilityaccuracyinterpretabilityorganizational skillsleadershipadaptability