Solution Architect – Python with GenAI

EPAM Systems India Pvt Ltd; Bengaluru; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

EPAM Systems India Pvt Ltd is seeking a Solution Architect with deep GenAI expertise to engineer enterprise GenAI solutions for production. You will lead architectural explorations, build reusable blocks, and shape standards for LLM-powered apps at scale.

You will drive end-to-end GenAI architectures, integrate with multi-cloud platforms, and oversee Docker/Kubernetes deployments while mentoring teams and ensuring robust system designs.

Qualifications

• 9–14 years of software development and design experience.
• Advanced Python for production environments.
• Experience with microservices, FastAPI, Redis, Elasticsearch and Kafka.
• GenAI applications delivery at scale (Agents, RAG, LLMOps).

Responsibilities

• Develop end-to-end GenAI architecture solutions for enterprise needs.
• Create reusable accelerator assets and reference solutions.
• Lead technical discovery meetings and support engineering teams.
• Define evaluation frameworks and standards for LLM-based apps.
• Oversee cloud integration across AWS, Azure or GCP.
• Manage Docker and Kubernetes deployment and orchestration.
• Mentor and share knowledge across the architecture community.
• Ensure production-grade Python applications and scalable designs.
• Guide ongoing improvements to system architecture.

Skills

Python (production)

GenAI applications

Solution architecture

Microservices

FastAPI

Redis

Elasticsearch

Kafka

Docker

Kubernetes

LangGraph

LangChain

RAG

Tools

Docker

Kubernetes

FastAPI

Redis

Elasticsearch

Kafka

LangGraph

LangChain

Job description

Our growing organization needs a Solution Architect with expertise in Python and Generative AI to engineer and roll out enterprise-level GenAI solutions capable of operating reliably in production. Within our Solution Architecture team, you'll steer technical exploration projects, develop reusable building blocks, and contribute to shaping standards for LLM-powered applications.

Responsibilities

• Develop end-to-end GenAI architecture solutions, covering RAG approaches, Agents, and Multi-Agent designs, tailored to large enterprise needs.
• Build reusable accelerator assets and reference solutions to create consistency across delivery.
• Head up technical discovery meetings and give practical, on-the-ground support to engineering teams.
• Establish evaluation frameworks and outline standards guiding the creation of LLM-based applications.
• Work with multiple teams to confirm that architectural approaches remain scalable and manageable over the long haul.
• Engineer microservices systems by drawing on recognized patterns and modern technology frameworks.
• Oversee integration efforts tied to cloud infrastructure across platforms such as AWS, Azure, or GCP.
• Handle container deployment and orchestration responsibilities via Docker and Kubernetes.
• Assess and determine fitting vector database technologies, like Pinecone, Weaviate, or Chroma, to power GenAI solutions.
• Roll out LLMOps techniques and monitoring systems to elevate the quality of production releases.
• Aid in prompt engineering work and RAG evaluation to strengthen application dependability.
• Take part in mentoring programs and share insights across the architecture community.
• Maintain rigorous coding practices for Python applications intended for production use.
• Guide ongoing efforts to enhance system architecture design and solution scalability.

Requirements

• Experience spanning 9 to 14 years in software development, with strong expertise in solution architecture and system design.
• Advanced Python capabilities focused on writing code fit for production environments.
• Skill set covering microservices architecture, design patterns, FastAPI, Redis, Elasticsearch, and Kafka.
• Deep hands-on experience creating GenAI applications, including Agents, MCP, RAG, Agentic RAG, and GraphRAG.
• Strong knowledge of LangGraph, LangChain, and other orchestration technologies.
• Practical background evaluating LLMs and RAG frameworks, along with handling prompt management tasks.
• Proven capability delivering GenAI applications that scale effectively in production.
• Direct experience with cloud environments, including AWS, Azure, or GCP.
• Familiarity with containerization approaches, particularly Docker and Kubernetes.
• Understanding of vector database platforms, such as Pinecone, Weaviate, or Chroma.
• Solid comprehension of LLMOps principles and the monitoring tools tied to them.
• Strong leadership abilities appropriate for directing engineering teams.
• Capability to work in client-facing scenarios while collaborating effectively with teams.
• Solid English language skills, both spoken and written, at a B2 level or higher.

Nice to have

• Experience with conventional machine learning techniques, including feature engineering, model training, and evaluation.
• Familiarity with knowledge graph principles and fine-tuning strategies.
• Previous exposure to consulting work or roles centered on direct client interaction.