Applied AI Engineer - LangChain/LangGraph

Incanus Technologies India

About the role

This is a remote applied AI engineering role for an early-career engineer based anywhere in India, with one to five years of experience. You'll connect foundation models and machine learning pipelines to production software, building RAG systems, agent workflows, APIs, and evaluation controls. The role suits someone comfortable with Python backend development and the operational requirements of reliable AI products.

What you’ll do

  • Integrate LLMs, foundation models, and custom ML pipelines into software products.
  • Build and maintain RAG architectures, vector indexes, and agent workflows.
  • Improve inference latency, cost, and throughput with caching, quantization, and batching.
  • Work with product and backend teams on REST APIs and AI microservices.
  • Create evaluation, monitoring, and guardrail systems for production outputs.

What they’re looking for

  • Bachelor's or master's degree in computer science, data science, AI, or a related field.
  • At least one year of software engineering experience with production AI or ML applications.
  • Strong Python and backend framework skills such as FastAPI, Flask, or Django.
  • Hands-on experience with LangChain, LlamaIndex, AutoGen, or similar tools.
  • Experience using OpenAI, Anthropic, Hugging Face, or comparable model APIs.
  • Practical experience with vector databases such as Pinecone, Qdrant, Milvus, Weaviate, or Chroma.
  • Understanding of Git, Docker, REST APIs, and database design.

Nice to have

  • Fine-tuning experience with PEFT, LoRA, or QLoRA.
  • Exposure to MLflow, Weights & Biases, BentoML, or vLLM.
  • Familiarity with AWS Bedrock, SageMaker, Vertex AI, or Azure OpenAI.
  • Experience with Ragas, DeepEval, or similar evaluation tools.

What’s on offer

  • Remote work from anywhere in India.
  • Competitive salary package with equity options.
  • Cloud-compute budget and access to AI hardware or APIs.
  • Flexible work environment.
  • Health insurance and a learning stipend for AI certifications and conferences.
  • Direct ownership of high-impact AI products.

Questions about this role

Can this applied AI role be done remotely?

Yes. The posting says candidates may work from anywhere in India.

How much experience is required?

The listed range is one to five years, with at least one year of software engineering experience involving production AI or ML applications.

What degree is requested?

A bachelor's or master's degree in computer science, data science, AI, or a related field is listed under required qualifications.

Which AI frameworks are mentioned?

The posting names LangChain, LlamaIndex, and AutoGen, with LangChain and LangGraph highlighted in the listing.

Related roles

Senior Applied AI Engineer

Weekday Partner Network · India, India

Weekday Partner Network is listing a senior Applied AI Engineer role in India for candidates with four to seven years of experience. The work covers AI model development, deployment, integration, and optimization.

RemoteSeniorFull-time ₹2,000,000 – ₹7,000,000 a year
Applied AIAI ModelsAlgorithm OptimizationAI Deployment
6 days ago

Applied AI Engineer

Perplexity AI · Bengaluru, India

Perplexity AI is hiring a mid-level Applied AI Engineer for its India team to build retrieval, model-orchestration and evaluation systems remotely from a Bengaluru anchor. The role requires production engineering, retrieval or RAG experience and LLM evaluation skills.

RemoteMid level
Applied AIProduction EngineeringInformation RetrievalRAG +3
Date not stated

Solutions Engineer AI Engineer

Weekday Partner Network · Remote (India), India

Remote solutions engineering role in India for building conversational voice and video AI applications in life sciences. The role suits engineers with at least three years of Python, API, LLM, or AI solutions experience.

RemoteMid levelFull-time ₹2,500,000 – ₹5,000,000 a year
PythonAPIsLarge Language ModelsAI Application Architecture +3
5 days ago

AI Engineer – Generative AI

AppZime Technologies · Hyderabad, India · Ahmedabad, India · Indore, India

Onsite AI Engineer role in Hyderabad, Ahmedabad, or Indore building generative-AI and agentic systems. The position suits an engineer with at least six years of experience across LLMs, RAG, Python, and cloud deployment.

On-siteFull-time $47,000 – $60,200 a year
LLMRAGGenerative AILangChain +14
9 days ago

Applied AI Engineer

KeeMakr.ai · Bengaluru, India

Onsite Applied AI Engineer role in Bengaluru focused on LLM applications, agentic workflows, retrieval systems and backend services. It suits an experienced Python engineer who can take AI features into production.

On-siteFull-time ₹4,000,000 – ₹6,000,000 a year
PythonGenerative AILarge Language ModelsLangChain +16
Date not stated

Applied AI Engineer

Zenopsys · Bengaluru, India

Hybrid Applied AI Engineer role in Bengaluru focused on document intelligence, RAG and AI agents for regulated life-sciences workflows. It suits an AI engineer who can build reliable, source-grounded LLM products.

HybridFull-time ₹2,500,000 – ₹3,000,000 a year
PythonMachine LearningGenerative AILarge Language Models +11
Date not stated