Ascendion - Senior GenAI Engineer - RAG/LLM

Description :

We are seeking a highly skilled and innovative Senior GenAI Engineer to design, develop, and deploy next-generation AI-powered products and platforms. The ideal candidate will have strong expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI Agents, Vector Databases, and scalable cloud-native architectures.

You will work closely with Product, Engineering, Data Science, and Business teams to build enterprise-grade Generative AI solutions that drive automation, intelligence, and business value. This role requires hands-on technical leadership in architecting production-ready GenAI applications, optimizing AI systems, and mentoring engineering teams.

Key Responsibilities :

- Design, build, and deploy enterprise-scale Generative AI applications using state-of-the-art LLMs.

- Develop advanced RAG (Retrieval-Augmented Generation) systems to improve response accuracy, relevance, and contextual understanding.

- Build and optimize AI agents capable of autonomous reasoning, decision-making, workflow orchestration, and tool integration.

- Design prompt engineering frameworks and evaluation methodologies for high-quality AI outputs.

- Develop multi-agent systems and agentic workflows using LangChain, LangGraph, CrewAI, AutoGen, or similar frameworks.

- Fine-tune, customize, and optimize Large Language Models for specific business use cases.

- Implement model evaluation pipelines focusing on accuracy, hallucination reduction, latency, and cost optimization.

- Build guardrails, safety mechanisms, and monitoring frameworks for AI applications.

- Optimize token usage, context management, retrieval strategies, and inference performance.

- Architect scalable knowledge retrieval systems using Vector Databases.

- Design ingestion pipelines for structured and unstructured data.

- Implement semantic search, hybrid search, reranking, chunking strategies, metadata filtering, and retrieval optimization.

- Improve retrieval accuracy through embeddings optimization and relevance tuning.

- Design scalable microservices-based AI platforms.

- Build distributed systems capable of serving high-volume AI workloads.

- Develop APIs and backend services for AI applications.

- Architect cloud-native solutions using AWS, GCP, or Azure services.

- Implement Kubernetes-based deployments for scalable and resilient AI systems.

- Establish CI/CD pipelines for AI model deployment and lifecycle management.

- Implement observability, monitoring, logging, and performance tracking for GenAI applications.

- Build automated testing frameworks for prompts, agents, and AI workflows.

- Ensure security, compliance, governance, and responsible AI practices

- Collaborate with Product Managers, Architects, Data Scientists, and Engineering teams to define AI strategies.

- Provide technical leadership and mentorship to junior engineers.

- Conduct architecture reviews and establish engineering best practices.

- Stay updated with emerging GenAI technologies, frameworks, and industry trends.

Required Skills & Qualifications :

Programming :

- Expert-level proficiency in Python.

- Strong knowledge of software engineering principles, design patterns, and clean coding practices.

- Experience with FastAPI, Flask, Django, or similar frameworks.

Generative AI & LLMs :

- Extensive hands-on experience with :

1. OpenAI GPT Models

2. Claude

3. Gemini

4. Llama

5. Mistral

6. Open-source LLM ecosystems

7. Prompt Engineering

8. Function Calling

9. Tool Usage

10. Context Management

11. Fine-Tuning

12. Model Evaluation

RAG Systems :

- Deep expertise in :

i. Retrieval-Augmented Generation (RAG)

ii. Knowledge Retrieval Architectures

iii. Hybrid Search

iv. Semantic Search

v. Query Expansion

vi. Reranking Techniques

vii. Context Compression

Agent Frameworks :

- LangChain

- LangGraph

- CrewAI

- AutoGen

- Agentic Workflow Design

- Multi-Agent Systems

Vector Databases :

- Pinecone

- Weaviate

- ChromaDB

- Milvus

- Qdrant

- Elasticsearch/OpenSearch Vector Search

- FAISS

Cloud & Infrastructure :

- AWS / Azure / GCP

- Kubernetes

- Docker

- Terraform

- Cloud-Native Architectures

- Serverless Deployments

- Distributed Systems

- High Availability Systems

- Scalability Patterns

- Event-Driven Architectures

- Message Queues

- Distributed Computing Concepts

- Performance Optimization

- Experience building AI copilots, chatbots, virtual assistants, and enterprise search platforms.

- Exposure to multimodal AI systems (text, image, audio, video).

- Knowledge of Graph Databases and Knowledge Graphs.

- Experience with ML frameworks such as PyTorch and TensorFlow.

- Understanding of LLM observability platforms like LangSmith, Weights & Biases, Arize, Helicone, or TruLens.

- Experience in AI governance, compliance, and responsible AI frameworks.

- Familiarity with data engineering and large-scale data processing.

- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or related field.

- Candidates from premier institutes preferred.