AI Engineer

Avisoft; United States; Remote; USD 140,000 - 200,000; Full time

Job summary

Avisoft is seeking an experienced AI Engineer to design, build, and deploy enterprise-grade Generative AI solutions. The ideal candidate should have strong expertise in LLMs, RAG pipelines, Agentic AI frameworks, Python, and cloud platforms, with proven experience developing scalable AI applications from architecture to production.

The role requires excellent problem-solving, stakeholder communication, and the ability to drive AI initiatives independently.

Qualifications

• 8+ years of software engineering experience with strong expertise in Generative AI/LLMs.
• Strong proficiency in Python.
• Hands-on experience building RAG applications and Agentic AI solutions.

Responsibilities

• Design and develop production-ready Generative AI and LLM-powered applications.
• Build scalable RAG pipelines using vector databases and retrieval optimization techniques.
• Architect and implement Agentic AI solutions using LangGraph, LangChain, CrewAI, AutoGen, Semantic Kernel, or similar frameworks.
• Develop multi-agent workflows, tool integrations, memory management, and AI orchestration.
• Build REST APIs using Python (FastAPI/Flask) and integrate AI solutions with enterprise systems.
• Optimize AI applications through prompt engineering, evaluation frameworks, guardrails, and hallucination mitigation.
• Deploy and manage AI workloads on AWS, Azure, or GCP.
• Collaborate with business stakeholders to gather requirements, propose AI solutions, and drive production deployments.

Skills

Generative AI/LLMs

Python

RAG applications

Agentic AI

LLM evaluation

REST APIs

Cloud platforms

Embedding & retrieval

Tools

LangGraph

LangChain

CrewAI

AutoGen

Semantic Kernel

Pinecone

Chroma

Weaviate

Milvus

FAISS

pgvector

Job description

Job Summary

We are seeking an experienced AI Engineer to design, build, and deploy enterprise-grade Generative AI solutions. The ideal candidate should have strong expertise in LLMs, RAG pipelines, Agentic AI frameworks, Python, and cloud platforms, with proven experience developing scalable AI applications from architecture to production. This role requires excellent problem-solving, stakeholder communication, and the ability to drive AI initiatives independently.

Key Responsibilities

• Design and develop production-ready Generative AI and LLM-powered applications.
• Build scalable RAG pipelines using vector databases and retrieval optimization techniques.
• Architect and implement Agentic AI solutions using LangGraph, LangChain, CrewAI, AutoGen, Semantic Kernel, or similar frameworks.
• Develop multi-agent workflows, tool integrations, memory management, and AI orchestration.
• Build REST APIs using Python (FastAPI/Flask) and integrate AI solutions with enterprise systems.
• Optimize AI applications through prompt engineering, evaluation frameworks, guardrails, and hallucination mitigation.
• Deploy and manage AI workloads on AWS, Azure, or GCP.
• Collaborate with business stakeholders to gather requirements, propose AI solutions, and drive production deployments.

Mandatory Skills

• 8+ years of software engineering experience with strong expertise in Generative AI/LLMs.
• Strong proficiency in Python.
• Hands-on experience building RAG applications and Agentic AI solutions.
• Experience with LangGraph, LangChain, CrewAI, AutoGen, Semantic Kernel, or similar frameworks.
• Expertise in Vector Databases (Pinecone, Chroma, Weaviate, Milvus, FAISS, pgvector, etc.).
• Strong understanding of embeddings, prompt engineering, retrieval optimization, and LLM evaluation.
• Experience with FastAPI/Flask, REST APIs, SQL, and cloud platforms (AWS/Azure/GCP).
• Excellent communication and stakeholder management skills.

Preferred Skills

• Experience with Master Data Management (MDM), data governance, or metadata platforms.
• Exposure to Collibra, Tableau, or similar enterprise tools.
• Domain experience in Pharma, Life Sciences, or Clinical Data.
• Consulting or client-facing experience.