GenAI Engineer What are we doing -
Our intention is to bring a new age digital experience for our employees for our enabling functions. To redefine how various departments interact & collaborate, adding ease, effectiveness and convenience with each and everything we do for our clients.
Your role is to build awesome digital experience that users love and will build out our internal systems ecosystem to support the same. You will be guided by your deep understanding of our internal processes as well as digital innovators, and your close relationships with other stakeholders.
Job Description:
- Strong proficiency in Python (async, typing, packaging, unit testing); solid grounding in data structures and algorithms
· Hands‑on with AWS—specifically Amazon Bedrock, SageMaker, S3, Lambda, Step Functions, CloudWatch, IAM; vector search - pgvector, OpenSearch vector
· Working knowledge of LangChain/LangGraph, RAG architectures, prompt design & evaluation; familiarity with guardrails (policy, PII/Secrets redaction), HITL patterns
· Experience with ETL/data processing (Pandas / Spark) and NoSQL/SQL stores (DynamoDB/Postgres)
· Proficiency with Git, CI/CD (GitHub Actions/Jenkins), Docker, and basic Kubernetes concepts
· Understanding of microservices and event‑driven integrations (queues, webhooks); observability (logging, metrics, tracing)
· Bonus: ReactJS for full‑stack prototypes; Copilot usage patterns for engineering productivity; document pipelines
· What you must bring (Experience)
· 4–7 years of software engineering experience GenAi services focused, including 2+ years building or integrating GenAI/ML solutions
· Bachelor’s degree in Engineering/Computer Science (or equivalent)
· Practical understanding of IT + business concepts and how AI features translate to measurable outcomes
· Responsibilities – What will you do
· Design and develop AI‑powered backend systems and services that leverage Bedrock (model selection, orchestration), RAG pipelines (indexing, retrieval, evaluation), and S3 content sources
· Build secure APIs that integrate AI features into internal apps; partner with UI teams on full‑stack delivery
· Implement prompt engineering, evaluation harnesses, safety filters, and HITL review workflows; measure quality (precision, hallucination rate, latency, cost)
· Create ETL/ingestion jobs and embeddings pipelines; optimize chunking, metadata, and retrieval performance
· Productionize with CI/CD, IaC, logging/monitoring, and cost/latency optimization; contribute to runbooks and SLOs
· Collaborate with product owners, domain SMEs, data engineering, security, and compliance to align on value, controls, and go‑live readiness
· Champion reusability by packaging patterns (RAG, agents, evaluation) as internal accelerators and documenting best practices
· Nice‑to‑have / Good‑to‑have
· Experience with agentic workflows (task decomposition, tools, function‑calling) and evaluation frameworks
· Knowledge of SageMaker model endpoints, fine‑tuning/parameter‑efficient tuning, and feature stores
· Familiarity with pgvector/OpenSearch, prompt/test case libraries, cost observability, and Copilot productivity dashboards
Pay: ₹1,200,000.00 - ₹1,800,000.00 per year
Benefits:
- Health insurance
- Provident Fund
Application Question(s):
- What is your current CTC & Notice Period?
Experience:
- Software deployment: 5 years (Preferred)
- Gen AI: 2 years (Preferred)
- Python: 5 years (Preferred)
- AWS: 4 years (Preferred)
Location:
- Gurugram, Haryana (Required)
Work Location: In person
