🐍 Python Developer – AI Implementation & Optimization Specialist

🌟 Position Overview

Python Developer

Atcuality

🧠 Key Responsibilities🤖 AI Implementation & Integration

• Integrate

  LLMs via AWS Bedrock

  , OpenAI, or Claude APIs for clinical use cases
• Build scalable, secure

  Python APIs and wrappers

  for model consumption
• Implement

  streaming AI responses

  and fallback mechanisms for fail-safe delivery
• Configure

  multi-agent decision orchestration

  for healthcare workflows
• Build

  prompt+context orchestration layers

  that ensure factual accuracy and compliance

☁️ AWS Bedrock Configuration & Management

• Set up and manage Bedrock endpoints for

  Claude, Titan, and Llama 3

• Configure

  access control, PrivateLink, VPC endpoints

  , and

  model A/B testing

• Monitor performance, scaling, latency, and token metrics in real time
• Implement

  model versioning and failover strategies

🧮 Token Optimization & Cost Control

• Build systems for

  token counting, estimation, and analytics

• Develop

  prompt compression

  , token-aware caching, and context window managers
• Implement

  budgeted inference

  logic for controlled spending
• Monitor token usage via dashboards and alerts

✍️ Prompt Engineering & Optimization

• Design healthcare-safe prompts using

  few-shot

  ,

  chain-of-thought

  , and

  constitutional AI

  strategies
• Create

  dynamic prompt builders

  ,

  version control

  , and

  testing harnesses

• Implement prompt injection detection and sanitization
• Measure and improve

  prompt accuracy, safety, and efficiency

🔒 Healthcare AI Compliance & Security

• Ensure

  HIPAA and PHI security

  in all prompt interactions and API calls
• Integrate

  PHI redaction

  , audit trails, and explanation consistency
• Implement

  content filtering, reasoning traceability

  , and medical fact validation
• Design AI systems that comply with

  FHIR, HITECH

  , and

  HITRUST controls

⚙️ Technical Implementation

• Write clean, modular, and

  async-friendly Python 3.10+ code

• Use

  FastAPI

  ,

  Pydantic

  , and

  LangChain

  for LLM orchestration
• Build

  comprehensive test suites

  using Pytest
• Maintain documentation for all AI-based endpoints and workflows
• Optimize for low-latency and production-scale LLM workloads

✅ Required Qualifications👨‍💻 Technical Skills

• 3–5 years of Python development

  , with focus on backend AI systems

• 1+ years of LLM experience

  (OpenAI, Claude, Llama, or similar)
• Hands-on with

  AWS Bedrock

  or equivalent managed LLM service
• Strong understanding of

  prompt engineering and token budgets

• Proficiency with

  asyncio

  ,

  aiohttp

  , and async concurrency patterns
• REST API development using FastAPI or Flask

🔧 Core Competencies

• Understanding of

  transformers, attention mechanisms

  , and LLM internals
• Familiarity with

  LangChain

  ,

  LlamaIndex

  ,

  embedding models

  , and

  vector stores

• Experience with

  retrieval-augmented generation (RAG)

  patterns
• Ability to handle

  streamed responses, retries

  , and

  multi-agent orchestration

• Prompt design for

  accuracy, context compression, and LLM alignment

💎 Preferred Qualifications

• Healthcare domain experience

  or exposure to clinical data workflows
• Knowledge of

  HIPAA, FHIR, DICOM

  , or

  ICD-10 medical codes

• Experience with

  Anthropic Claude API

  and

  OpenAI migration strategies

• Proficiency with

  WebSockets

  ,

  event-driven agents

  , and

  prompt chaining

• Understanding of

  RLHF, constitutional AI

  , or reward modeling
• Experience with

  model quantization, optimization

  , or

  open-source AI tools

• Contributions to open-source LLM or prompt engineering frameworks

🧰 Technical Environment

• Languages

  : Python 3.10+, TypeScript (for frontend integrations)

• AI Platforms

  : AWS Bedrock, OpenAI, Claude

• Frameworks

  : FastAPI, LangChain, Pydantic, asyncio

• Vector DBs

  : Pinecone, Weaviate

• Databases

  : PostgreSQL, Redis

• Monitoring

  : Datadog, CloudWatch, Weights & Biases

• Infrastructure

  : AWS, Docker, Kubernetes

• Version Control

  : Git, GitHub, GitLab

🎁 What We Offer

• Competitive salary based on experience and impact
• Comprehensive health, dental, and vision insurance
• Flexible

  remote/hybrid work setup

  with Jamshedpur base
• Stock options and equity participation in the company’s AI product stack
• Work on

  impactful, compliant AI healthcare systems

• Paid time off, wellness support, and parental leave policies

📤 Application Requirements

📧 career@atcuality.com

1. Updated resume focused on Python, AI integration, and LLM usage
2. GitHub portfolio or code samples showing AI/LLM-related work
3. Short cover letter explaining your

   prompt engineering philosophy

4. Blog posts or public demos (if applicable)

🧪 Interview Process

1. Initial HR screening call

   (30 mins)

2. Python + AI coding task

   (take-home or live)

3. LLM and prompt engineering deep dive

   (90 mins)

4. System design for AI workflow orchestration

   (60 mins)

5. Live prompt optimization exercise

   (45 mins)

6. Team culture fit interview

   (45 mins)

7. Reference checks + offer 🚀

💡 Why This Role Matters

AI thinks, responds, and behaves in a clinical setting

Aarna Tech Consultants Pvt. Ltd. (Atcuality)

We encourage applicants from diverse and non-traditional tech backgrounds to apply.