AI Engineer
Ankit Verma's Organization
- Experience
- 3+ years
- Location
- Remote
- Python
- REST APIs
- SQL
- NoSQL
- AWS
- GCP
- Azure
- OpenAI
About the role
Ship production-ready AI features that users rely on daily. Build reliable, scalable, and secure AI systems from prototype to production. Optimize AI system quality, latency, and cost in production. Integrate AI into core product experiences across teams.
What you’ll do
- Design and develop AI-powered applications using Large Language Models (LLMs).
- Build production-grade RAG (Retrieval-Augmented Generation) systems.
- Develop AI agents capable of reasoning, planning, and tool usage.
- Create scalable backend services that power AI features.
- Design prompts, evaluation pipelines, and guardrails for AI systems.
- Fine-tune and optimize models when required.
- Integrate third-party AI APIs and open-source models.
What we’re looking for
Must have
- Python
- REST APIs
- SQL
- NoSQL
- AWS
- GCP
Nice to have
- TypeScript
- JavaScript
- Kubernetes
- React
- Next.js
- Tailwind CSS
What makes this role challenging
- Building production-grade RAG and agent systems that are reliable, not just demo-quality.
- Optimizing the trade-off between model quality, latency, and cost at scale.
- Designing robust evaluation and guardrail systems to prevent AI hallucinations and ensure output quality.
- Keeping pace with the rapidly evolving landscape of foundation models and AI frameworks to make sound architectural decisions.
What success looks like
- First 30 days
- Ramp up on the existing codebase, tooling, and AI infrastructure. Ship a small, well-defined AI feature or improvement to production.
- By 90 days
- Own a significant AI feature or system end-to-end, from design to production monitoring. Establish evaluation pipelines and improve a key quality or latency metric.
- First year
- Drive the technical direction for a major AI product area. Set standards for AI engineering practices, mentor peers, and consistently deliver high-impact, reliable AI systems.
Tech stack
- OpenAI
- LLM integration
- Python
- Drupal
- Cloudflare CDN
- Google Universal Analytics
- classification models
- AI triage engine
- risk scoring models
- document generation
About Ankit Verma's Organization
PrivateCourt is a cloud-based online dispute resolution (ODR) platform founded in 2019, based in Mumbai, India. It connects individuals and businesses with legal professionals to resolve disputes through arbitration, mediation, and conciliation. The company is evolving into a product-led legal-tech ecosystem, building AI-powered capabilities including case triage, risk scoring, and document generation.
Legal Tech / Online Dispute Resolution · Bootstrapped · 11-50 employees
AI Engineer
About the role
We are looking for an AI Engineer to design, build, and deploy AI-powered products that solve real business problems. You will work across the full AI development lifecycle—from experimenting with the latest foundation models to building production-ready systems that are scalable, reliable, and secure.
This role is ideal for someone who enjoys shipping products, working with modern LLMs, and building AI systems that users rely on every day.
---
Responsibilities
- Design and develop AI-powered applications using Large Language Models (LLMs).
- Build production-grade RAG (Retrieval-Augmented Generation) systems.
- Develop AI agents capable of reasoning, planning, and tool usage.
- Create scalable backend services that power AI features.
- Design prompts, evaluation pipelines, and guardrails for AI systems.
- Fine-tune and optimize models when required.
- Integrate third-party AI APIs and open-source models.
- Build data pipelines for ingestion, embedding, indexing, and retrieval.
- Implement vector databases and semantic search systems.
- Monitor model performance, latency, cost, and quality in production.
- Work closely with product, design, and engineering teams to ship AI features quickly.
- Stay up to date with the latest developments in AI and recommend improvements.
---
Required qualifications
- Bachelor's degree in Computer Science or equivalent practical experience.
- 3+ years of software engineering experience.
- 2+ years building AI or Machine Learning applications.
- Strong programming skills in Python.
- Experience with TypeScript or JavaScript is a plus.
- Strong understanding of REST APIs and backend development.
- Experience with SQL and NoSQL databases.
- Familiarity with cloud platforms such as AWS, GCP, or Azure.
- Strong problem-solving and communication skills.
---
Required AI skills
Large Language Models
- OpenAI
- Anthropic Claude
- Gemini
- Llama
- Mistral
AI Frameworks
- LangChain
- LangGraph
- LlamaIndex
- Vercel AI SDK
- OpenAI Agents SDK (or equivalent)
Retrieval & Search
- RAG architectures
- Embedding models
- Hybrid search
- Semantic search
- Re-ranking techniques
Vector Databases
Experience with one or more
- Pinecone
- Weaviate
- Qdrant
- Milvus
- pgvector
AI Engineering
- Prompt engineering
- Structured outputs
- Function calling / Tool calling
- AI evaluations
- Model benchmarking
- Context management
- Memory systems
- Agent orchestration
---
Backend skills
Experience with one or more
- Python (FastAPI, Flask)
- Node.js
- Express
- NestJS
Knowledge of
- PostgreSQL
- Redis
- Docker
- Kubernetes (preferred)
- Message queues
- Background job processing
---
Frontend (nice to have)
- React
- Next.js
- TypeScript
- Tailwind CSS
---
MLOps (preferred)
- Model deployment
- ML pipelines
- Experiment tracking
- Model versioning
- Monitoring
- CI/CD for AI systems
- GPU inference optimization
---
Nice to have
- Experience with multimodal AI (image, audio, video).
- Fine-tuning open-source models.
- Experience with OCR, speech recognition, or computer vision.
- Knowledge of MCP (Model Context Protocol).
- Experience building AI copilots or autonomous agents.
- Experience with self-hosted LLM infrastructure.
- Contributions to open-source AI projects.
- Experience evaluating AI quality and hallucination reduction.
---
What You'll Build
- AI Agents
- Internal AI copilots
- Chatbots
- Document intelligence systems
- Workflow automation
- Knowledge management platforms
- AI search
- Content generation tools
- Multi-agent systems
- AI-powered SaaS products
---
What we offer
- Opportunity to work with cutting-edge AI technologies.
- Ownership of impactful AI products.
- Fast-paced engineering culture.
- Flexible work environment.
- Competitive salary and benefits.
- Learning budget for AI conferences, courses, and certifications.
- Access to the latest AI tools and models.
---
Hiring process
- Resume Screening
- Technical Assessment
- AI System Design Interview
- Coding Interview
- Culture & Team Fit Interview
- Final Discussion
---
Preferred experience
- Production AI systems
- LLM applications at scale
- AI infrastructure
- Backend engineering
- Distributed systems
- API design
- Cloud-native development
---
Success in This role
Within your first few months, you will
- Ship production-ready AI features.
- Build reliable AI workflows with measurable quality.
- Improve model performance while optimizing latency and cost.
- Collaborate across teams to integrate AI into core product experiences.
- Continuously evaluate and adopt emerging AI technologies where they add value.