Gen AI Engineer

Job Description

As a GenAI Engineer, you will develop next-generation AI applications that transform enterprise automation and intelligence. This role demands deep technical expertise and deliver scalable AI & GenAI solutions powered by state-of-the-art LLMs like Gemini, Vertex AI etc

You will:

• Design secure, high-performance APIs and orchestrate multi-agent systems for distributed workflows.
• Implement Retrieval-Augmented Generation (RAG) pipelines for intelligent, context-aware applications.
• Integrate LLMs into mission-critical banking workflows for email automation processing, semantic search across financial data, customer query automation, and advanced NLP capabilities etc
• Collaborate with Client side GenAI architects, product leaders, and security teams to deliver solutions
• Continuously innovate and experiment with new LLM models, prompt engineering techniques, and orchestration patterns.

Key Responsibilities

• API Development: Build REST endpoints with FastAPI/Flask, auto-generate docs (Swagger), implement rate limiting, OAuth2, and observability.
• LLM Integration: Optimize prompts, implement RAG pipelines, integrate Gemini, Vertex AI, OpenAI, Claude, Llama; monitor performance and run A/B tests.
• Multi-Agent Systems: Design distributed workflows using Celery, Kubernetes, Kafka/RabbitMQ; ensure resilience and fault tolerance.
• Experience with GCP components
• Data & Vector Search: Work with MySQL/PostgreSQL/MongoDB, Redis, and vector DBs (Pinecone, FAISS, Milvus).
• Experience with GenAI frameworks (LangChain, Hugging Face, EasyRAG).
• Experience building and deploying ML models for classification, regression, and clustering using frameworks like scikit-learn, XGBoost, TensorFlow/PyTorch.
• Hands-on experience with LangChain Agents, Google ADK, or similar frameworks for building agentic workflows.
• Cloud Expertise: Experience deploying and optimizing GenAI workloads on GCP (Vertex AI) and other cloud platforms.
• Strong understanding of feature engineering, model evaluation (ROC, AUC, precision/recall), and hyperparameter tuning for production-grade ML systems.
• Testing & Monitoring: Unit/integration tests (pytest), logging, tracing, metrics, and SLOs.

Critical Skills

• Python (FastAPI/Flask)
• LLM Integration & Prompt Engineering – Gemini, Vertex AI, Llama
• LangChain, RAG Pipelines
• Multi-Agent Architecture – Celery, Kubernetes, Kafka
• Vector Databases – PosgreSQL, , FAISS, Milvus ,Quadrant etc
• GCP

Qualifications

• Bachelor’s/Master’s/PhD in Computer Science, Statistics, Data Science, or related field.
• 8+ years of experience in AI/ML and data science roles.
• Proven track record of delivering production-grade AI models ,apps and solutions.

Compensation and Benefits

A candidate’s pay within the range will depend on their work location, skills, experience, education, and other factors permitted by law. This role may also be eligible for performance-based bonuses subject to company policies. In addition, this role is eligible for the following benefits subject to company policies: medical, dental, vision, pharmacy, life, accidental death & dismemberment, and disability insurance; employee assistance program; 401(k) retirement plan; 10 days of paid time off per year (some positions are eligible for need-based leave with no designated number of leave days per year); and 10 paid holidays per year.