Solution Architect – Python

EPAM Systems; Gurugram District; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

EPAM Systems in India is seeking an experienced Solution Architect specializing in Python and Generative AI to design enterprise-scale GenAI solutions for live production environments.

You will lead technical investigations, build reusable toolkits, and set guidelines for LLM-driven applications while mentoring the architecture team and collaborating with cross-functional engineering groups.

Qualifications

• 9 to 14 years in software development with solution architecture and system design.

Responsibilities

• Construct GenAI architectures for enterprise clients, including RAG, Agents and multi-agent setups.
• Create reusable accelerator tools and reference models to standardize delivery.
• Run technical discovery workshops and provide hands-on guidance to engineering teams.
• Set up evaluation frameworks and guidelines for LLM applications development.
• Ensure systems are scalable, maintainable and production-ready.
• Design microservices architectures using current patterns and frameworks.
• Direct integration of cloud platforms (AWS, Azure, GCP).
• Oversee containerization and orchestration with Docker and Kubernetes.
• Select vector databases (Pinecone, Weaviate, Chroma) to support GenAI initiatives.
• Apply LLMOps and monitoring frameworks to improve deployment outcomes.
• Contribute to prompt management and RAG evaluation work.
• Mentor and share expertise across the architecture team.
• Uphold production-quality Python coding standards.
• Champion continuous architectural improvements.

Skills

Python production-ready

Microservices architecture

Design patterns

Leadership

Client-facing

English (B2+)

Tools

FastAPI

Redis

Elasticsearch

Kafka

Docker

Kubernetes

LangGraph

LangChain

LLMOps

Pinecone

Weaviate

Chroma

Job description

We're growing our team and looking to add a Solution Architect who specializes in Python and Generative AI, tasked with designing and delivering enterprise-scale GenAI solutions suited for live production environments. Joining our Solution Architecture unit, you'll take the lead on technical investigation work, build out reusable toolkits, and help establish guidelines for LLM-driven applications.

Responsibilities

• Construct comprehensive GenAI architectures, encompassing RAG structures, Agents, and Multi-Agent setups, designed specifically for large enterprise clients
• Create reusable accelerator tools and reference models to standardize how solutions get delivered
• Run technical discovery workshops and provide hands‑on assistance directly to engineering teams
• Set up evaluation frameworks and establish guidelines governing the development of large language model (LLM) applications
• Partner with varied teams to ensure system architectures are built to scale properly and stay maintainable over time
• Design microservices architecture using proven patterns and up-to-date frameworks
• Direct the integration of cloud infrastructure components spanning platforms such as AWS, Azure, or GCP
• Take charge of containerization and orchestration tasks using Docker and Kubernetes
• Weigh options and select appropriate vector database platforms, including Pinecone, Weaviate, or Chroma, to support GenAI initiatives
• Apply LLMOps approaches and monitoring frameworks to improve production deployment outcomes
• Contribute to prompt management efforts and RAG evaluation work to increase application accuracy
• Engage in mentorship activities and share expertise throughout the wider architecture team
• Uphold rigorous production‑quality coding standards within Python‑based applications
• Champion continual improvements in system architecture and the scalability of solutions

Requirements

• 9 to 14 years of experience within software development, backed by a strong background in solution architecture and system design
• Advanced‑level Python programming ability with an emphasis on producing production‑quality code
• Proficiency spanning microservices architecture, design patterns, FastAPI, Redis, Elasticsearch, and Kafka
• Considerable experience developing GenAI applications, including work with Agents, MCP, RAG, Agentic RAG, and GraphRAG
• Thorough understanding of LangGraph, LangChain, and comparable orchestration technologies
• Direct experience conducting LLM and RAG evaluations, plus managing prompt‑related workflows
• Solid history of successfully delivering scalable, production‑ready GenAI applications
• Practical exposure to cloud platforms, including AWS, Azure, or GCP
• Working familiarity with containerization solutions such as Docker and Kubernetes
• Knowledge of vector database technologies, including options like Pinecone, Weaviate, or Chroma
• Clear understanding of LLMOps concepts and the tools used for monitoring
• Proven leadership qualities capable of guiding and directing engineering teams
• Ability to perform effectively in client‑facing roles while collaborating across teams
• Proficient English communication abilities, spoken and written, at a B2 level or higher

Nice to have

• Exposure to classic machine learning approaches, such as feature engineering, model training, and performance evaluation
• Knowledge of knowledge graph structures and fine‑tuning methodologies
• Background in consulting work or roles requiring direct client interaction