AI Prompt Engineer
Skills
About the role
This is a mid-level AI Prompt Engineer role building production prompt workflows and LLM components for client solutions and internal automation in India. You'll turn AI solution designs into tested systems with measurable quality, guardrails, retrieval, and structured outputs. The role is presented as remote and full-time.
What you’ll do
- Design, build, test, and refine prompts and prompt chains for production workflows.
- Create evaluation harnesses, guardrails, and regression tests.
- Connect LLM components to APIs, business data, and retrieval pipelines.
- Convert solution designs into production implementations with AI Specialists.
- Tune systems for accuracy, cost, latency, and safety using evaluation data.
- Document reusable patterns and expand the AI accelerator library.
What they’re looking for
- At least two years building software or AI/LLM components.
- Hands-on prompt development for real applications.
- Understanding of context windows, few-shot prompting, function calling, structured outputs, and RAG.
- Python or similar programming experience.
- Comfort with APIs, JSON, and Git.
- A test-and-measure approach to output quality.
- Clear written English and strong documentation habits.
- Ability to collaborate across time zones.
Nice to have
- Experience with Promptfoo, Ragas, or custom evaluation harnesses.
- Knowledge of embeddings, vector databases, and retrieval pipelines.
- Exposure to NetSuite, Salesforce, or business-process automation.
- Experience with agentic frameworks and orchestration.
What’s on offer
- Remote work in India.
- Full-time employment.
- Collaboration with an onshore and nearshore team.
Questions about this role
Is this role remote?
The listing presents it as a remote role for candidates in India.
How much experience is required?
At least two years of software or AI/LLM component experience is requested.
What tools and methods are mentioned?
The posting names Python, APIs, JSON, Git, RAG, structured outputs, Promptfoo, Ragas, embeddings, and vector databases.
What will I build?
You will build prompts, prompt chains, evaluation harnesses, guardrails, and LLM integrations.
Related roles
AI Engineer – Generative AI
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.
Solutions Engineer AI Engineer
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.
Generative AI/Agentic AI Engineer
Generative AI and agentic AI engineer role in Noida for a Python developer with four to six years of experience. The position focuses on LLM applications, multi-agent workflows, prompt engineering, RAG, and production integrations.
Senior AI-Native Engineer
Senior hybrid AI engineering role in Gurgaon for an engineer with five or more years of experience and production AI/ML background. You'll design agentic applications, evaluation frameworks, and monitored AI capabilities end to end.
Principal Engineer - Gen AI, LLM, RAG, Agentic AI
A principal engineering role at Wells Fargo in Bengaluru focused on GenAI, RAG and agentic AI architecture, evaluation and governance. Suited to a senior technical leader with deep GenAI stack and AI security expertise.
Senior AI-ML Engineer
A senior AI/ML engineering role at Ericsson in Bengaluru, building GenAI and machine learning capabilities across products and developer tooling.