Software Engineer - Agentic AI

Sysvine; Chennai District; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Sysvine is seeking an experienced AI/ML software engineer in Chennai to build intelligent AI agents and GenAI-powered SaaS solutions. You will work with LLMs, RAG, embeddings, and vector databases to deliver AI-driven features.

The role involves designing scalable AI applications, developing pipelines, and deploying cloud-native solutions. Strong Python, ML/NLP knowledge and collaboration with cross-functional teams are essential.

Qualifications

• 4 to 6 years of software engineering experience with Python.
• Hands-on with LLMs, GenAI, RAG, prompt engineering, embeddings, and vector search.
• Experience with LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, or similar frameworks.
• Proficiency with OpenAI, Claude, Gemini, Bedrock, Hugging Face, or equivalent AI platforms.
• Knowledge of Machine Learning, NLP, model evaluation, and AI best practices.
• Experience with PyTorch, TensorFlow, Scikit‑learn, or similar ML frameworks.
• Good SQL skills and experience with vector databases (Pinecone, Qdrant, FAISS, Weaviate, OpenSearch).
• Experience building REST APIs, cloud‑native applications, and deployments on AWS, Azure, or GCP.
• Familiarity with Docker, CI/CD, MLOps, MLflow, and production AI monitoring.
• Good analytical, communication, and problem‑solving skills with a passion for AI innovation.

Responsibilities

• Design, develop, and deploy scalable AI‑powered applications and APIs.
• Build and optimize RAG pipelines, AI agents, and prompt workflows.
• Fine‑tune, evaluate, and monitor LLMs for quality, performance, and reliability.
• Develop ML/AI pipelines using Python and modern AI frameworks.
• Integrate structured, unstructured, and vector data into AI solutions.
• Collaborate with Product, Engineering, QA, and domain experts to deliver AI‑driven features.
• Monitor model performance, cost, latency, and drift in production.
• Follow cloud‑native, secure, and scalable engineering practices.

Skills

Python

LLMs

GenAI

RAG

Prompt engineering

Embeddings

Vector search

REST APIs

Cloud deployments

Analytical skills

Tools

LangChain

LangGraph

LlamaIndex

CrewAI

AutoGen

PyTorch

TensorFlow

Scikit-learn

Pinecone

Qdrant

FAISS

Weaviate

OpenSearch

Job description

ID851 PostedAug 3, 2026 Openings2 Experience4-6 Years Annual Salary12 to 18L

Hot Duties:

• Build intelligent AI agents and GenAI-powered SaaS solutions using LLMs, RAG, and orchestration frameworks
• Develop enterprise AI applications integrating OpenAI, Claude, Gemini, Bedrock, or similar models
• Apply prompt engineering, semantic search, embeddings, and vector databases to solve business problems
• Leverage AI-assisted engineering to accelerate software design, development, testing, and delivery
• Drive innovation by evaluating and adopting emerging AI technologies

Duties:

• Design, develop, and deploy scalable AI-powered applications and APIs
• Build and optimize RAG pipelines, AI agents, and prompt workflows
• Fine-tune, evaluate, and monitor LLMs for quality, performance, and reliability
• Develop ML/AI pipelines using Python and modern AI frameworks
• Integrate structured, unstructured, and vector data into AI solutions
• Collaborate with Product, Engineering, QA, and domain experts to deliver AI-driven features
• Monitor model performance, cost, latency, and drift in production
• Follow cloud-native, secure, and scalable engineering practices

Requiremnets;

• 4 to 6 years of software engineering experience with Python expertise
• Hands‑on experience with LLMs, GenAI, RAG, prompt engineering, embeddings, and vector search
• Experience with LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, or similar frameworks
• Proficiency with OpenAI, Claude, Gemini, Bedrock, Hugging Face, or equivalent AI platforms
• Knowledge of Machine Learning, NLP, model evaluation, and AI best practices
• Experience with PyTorch, TensorFlow, Scikit‑learn, or similar ML frameworks
• Good SQL skills and experience with vector databases (Pinecone, Qdrant, FAISS, Weaviate, OpenSearch, etc.)
• Experience building REST APIs, cloud‑native applications, and deployments on AWS, Azure, or GCP
• Familiarity with Docker, CI/CD, MLOps, MLflow, and production AI monitoring
• Good analytical, communication, and problem‑solving skills with a passion for AI innovation