Senior Software Engineer

Overview

Senior Software Engineer role focused on designing, building and deploying production-grade AI-powered applications and intelligent agent frameworks, working closely with ML Engineers, Data Scientists, Product Managers and Cloud Architects.

What you'll do

• Design and develop Agentic AI workflows using frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or similar.
• Build and integrate LLM-powered applications using models from OpenAI, Anthropic, Meta (LLaMA), Mistral, or foundation models on cloud platforms.
• Implement Retrieval-Augmented Generation (RAG) pipelines, vector stores, and semantic search capabilities.
• Develop multi-agent orchestration systems with defined tool use, memory management, and reasoning loops.
• Evaluate, fine-tune, and optimize LLM behavior through prompt engineering and chain-of-thought design.
• Build high-performance, scalable RESTful APIs and async microservices using FastAPI and Python.
• Design clean, modular, and well-documented API contracts following OpenAPI/Swagger standards.
• Implement authentication, authorization, rate limiting, and security best practices across APIs.
• Develop event-driven and streaming architectures to support real-time AI inference pipelines.
• Deploy and manage AI workloads on AWS (SageMaker, Lambda, API Gateway, Bedrock, S3, ECS/EKS).
• Utilize Databricks for large-scale data processing, MLflow model tracking, and AI/ML pipeline orchestration.
• Build CI/CD pipelines and infrastructure-as-code (IaC) using tools like Terraform, AWS CDK, or similar.
• Ensure scalability, observability, and reliability through cloud-native monitoring and logging practices.
• Write clean, testable, production-ready Python code following software engineering best practices.
• Conduct code reviews and mentor junior engineers on GenAI patterns and best practices.
• Contribute to architectural decisions, technical roadmaps, and engineering documentation.
• Stay current with the rapidly evolving GenAI ecosystem and champion the adoption of emerging tools.

What you'll need

• 5–7 years of professional software engineering experience.
• Hands-on Python development in production environments.
• Experience with GenAI technologies including LLMs, RAG, embeddings, or prompt engineering.
• Building and deploying APIs using FastAPI or similar async Python frameworks.
• Experience working with AWS cloud services in a production environment.
• Hands-on experience with Databricks for data/AI workloads.
• Expert-level Python (async programming, type hints, Pydantic, dependency injection).
• FastAPI: routing, middleware, background tasks, OpenAPI spec generation.
• Experience with SQLAlchemy, Alembic, or async ORMs.
• Unit/integration testing with pytest, pytest-asyncio.
• Strong understanding of LLM internals, tokenization, context windows, and model behavior.
• Experience with LangChain / LangGraph / AutoGen / CrewAI or similar agentic frameworks.
• Familiarity with vector databases: Pinecone, Weaviate, pgvector, ChromaDB, or FAISS.
• Knowledge of RAG architectures, chunking strategies, and embedding models.
• Hands-on experience with OpenAI API, Anthropic Claude API, AWS Bedrock, or Hugging Face models.
• AWS Bedrock: LLM model invocation and management.
• AWS Lambda, API Gateway, ECS/EKS: serverless and containerized deployments.
• S3, DynamoDB, RDS/Aurora: data storage patterns.
• IAM, VPC, Secrets Manager: security and access control.
• Familiarity with AWS CDK or CloudFormation.
• Experience with Databricks Workflows, Delta Lake, Unity Catalog.
• Familiarity with MLflow for experiment tracking and model registry.
• Using Databricks for AI/BI or LLM serving pipelines.
• Docker and Kubernetes: containerization and orchestration.
• Git: branching strategies, PR workflows, GitOps.
• CI/CD: GitHub Actions, GitLab CI, Jenkins, or similar.
• Understanding of distributed systems, event streaming (Kafka or AWS Kinesis), and microservice patterns.
• Bachelor's or Master's degree in Computer Science, Software Engineering, Data Science, or a related technical field; equivalent practical experience and demonstrable project portfolio will be considered.

Nice to have

• Experience with multi-modal AI (vision + language models).
• Familiarity with Azure OpenAI Service or Google Vertex AI.
• Exposure to Terraform or Pulumi for infrastructure automation.
• Contributions to open-source AI/ML projects.
• Experience with GraphQL APIs.
• Background in data engineering or MLOps pipelines.
• AWS Certifications (Solutions Architect, ML Specialty).
• Databricks Certified Associate or Professional badge.

Details

• Location: Hyderabad, India (DVS, SEZ-1 – Orion B4; FL 7,8,9,11 / Divyasree 3).