LLM Engineer

Actowiz Solutions LLP; Ahmedabad District; Presencial; INR 600.000 - 900.000; Jornada completa

Descripción de la vacante

Actowiz Solutions LLP is seeking an AI/LLM developer to design and implement generative AI features within our applications. You will work with leading LLM APIs, embeddings, and vector databases to build robust AI capabilities from idea to prototype.

The role focuses on prompt engineering, RAG integration, and API-backed Python services, with a production-oriented mindset and a willingness to explore new models and tools.

Formación

• 1–2 years of experience in software development, AI/ML, or Generative AI.
• Strong programming knowledge in Python.
• Hands-on experience with at least one LLM API such as OpenAI, Google Gemini, or Open-source LLMs.
• Understanding of Prompt Engineering.
• Practical understanding of RAG.
• Experience with embeddings and vector databases.
• Basic experience with REST APIs.
• Familiarity with Git and GitHub.
• Good problem-solving and debugging skills.

Responsabilidades

• Build and integrate LLM-powered features into applications.
• Work with LLM APIs like OpenAI, Gemini, Anthropic, or similar platforms.
• Work with embeddings, vector databases, and semantic search.
• Design and improve prompts for accuracy, consistency, and performance.
• Implement function calling, structured outputs, and AI workflows.
• Develop APIs and backend services using Python.
• Evaluate LLM responses and improve accuracy and reliability.
• Debug and optimize LLM applications for performance, latency, and cost.
• Collaborate with developers and product teams to productionize AI features.
• Stay updated with new LLM models, frameworks, and Generative AI technologies.

Conocimientos

Python

LLM APIs

Prompt Engineering

RAG

Embeddings

REST APIs

Git

LLM evaluation

Debugging

Production AI

Herramientas

LangChain

LlamaIndex

LangGraph

Pinecone

Qdrant

Weaviate

Chroma

pgvector

FastAPI

Flask

PostgreSQL

MongoDB

Docker

AWS

Azure

GCP

Descripción del empleo

Key Responsibilities

• Build and integrate LLM-powered features into our applications.
• Work with LLM APIs such as OpenAI, Gemini, Anthropic, or similar platforms.
• Work with embeddings, vector databases, and semantic search.
• Design and improve prompts for accuracy, consistency, and performance.
• Implement function calling, structured outputs, and AI workflows.
• Develop APIs and backend services using Python.
• Evaluate LLM responses and improve accuracy and reliability.
• Debug and optimize LLM applications for performance, latency, and cost.
• Work with developers and product teams to integrate AI features into production.
• Stay updated with new LLM models, frameworks, and Generative AI technologies.

Required Skills

• 1–2 years of experience in software development, AI/ML, or Generative AI.
• Strong programming knowledge in Python.
• Hands‑on experience with at least one LLM API such as:
  • OpenAI
  • Google Gemini
  • Open‑source LLMs
• Understanding of Prompt Engineering.
• Practical understanding of RAG.
• Experience with embeddings and vector databases.
• Basic experience with REST APIs.
• Familiarity with Git and GitHub.
• Good problem‑solving and debugging skills.

Good to Have

• Experience with LangChain, LlamaIndex, or LangGraph.
• Experience with vector databases such as Pinecone, Qdrant, Weaviate, Chroma, or pgvector.
• Experience with FastAPI or Flask.
• Basic knowledge of PostgreSQL or MongoDB.
• Familiarity with Docker.
• Experience deploying applications on AWS, Azure, or Google Cloud.
• Understanding of LLM evaluation and observability.
• Exposure to AI agents and tool/function calling.

We are looking for someone who

• Has actually built LLM/Generative AI projects, not just completed courses.
• Can independently build a small AI feature from idea to working prototype.
• Understands the difference between a simple chatbot and a production‑grade LLM application.
• Is comfortable experimenting with different models and prompts.
• Can troubleshoot hallucinations, poor retrieval, and inconsistent LLM responses.
• Is eager to learn and keep up with the rapidly changing AI ecosystem.

Required Skills

langchain Llamaindex Qdrant/PgVector pinecone LLMAPIs AI python