Backend / AI Engineer
⚲ Warszawa, Mokotów
28 560–40 320 zł netto (+ VAT) / mies.
Wymagania
- Python
- FastAPI
- ECS
- Fargate
- Lambda
- API Gateway
- DynamoDB
- ElastiCache
- Bedrock
- Nova 2 Sonic
- Nova Micro
Opis stanowiska
Nasze wymagania:
Availability to maintain partial overlap with the MT zone.
Min. 5 years of experience in Python engineering.
Practice in developing high-performance, resilient backend services and APIs (FastAPI).
Strong practical knowledge of AI/ML concepts, especially LLM orchestration, Retrieval-Augmented Generation (RAG), and prompt engineering.
Expertise in AWS services, including ECS/Fargate, Lambda, API Gateway, DynamoDB, ElastiCache, and Bedrock services (Nova 2 Sonic, Nova Micro).
Familiarity with the Strands Agents SDK or other multi-agent architecture frameworks.
Mile widziane:
BS/MS in Computer Science, Mathematics, Statistics, or a related quantitative field
O projekcie:
Acaisoft is a company partnering with industry leaders across healthcare, telecom, fintech, and insurance, building Cloud, Data & AI solutions for fast-moving businesses.
Although we are a Poland-based company, most of our clients are based in the U.S., so flexibility around non-standard working hours is important for smooth collaboration across time zones.
Currently, we are looking for a Senior AI/Backend Engineer to join the team developing the AI Voice Dispatch Assistant. This is a critical role focused on building a scalable, production-ready multi-agent voice AI solution, running entirely within the client's AWS perimeter.
Zakres obowiązków:
AI Agent Development: Design, implement, and maintain the multi-agent system using the Strands Agents SDK (BidiAgent) on ECS/Fargate, ensuring per-session isolation, auto-scaling, and managing the Nova 2 Sonic BidirectionalStream lifecycle.
Core Backend Services: Develop and maintain the production FastAPI backend, including a centralized AHS API client library (Member Service, Dispatch, Coverage / Eligibility) with features such as Pydantic models for complex responses, per-call audit logging with field-level PII masking, and per-endpoint caching.
LLM Orchestration & RAG: Implement the triage super-agent for first-turn domain routing (Nova Micro) and delegate to specialized sub-agents. Integrate Bedrock Knowledge Bases (OpenSearch Serverless, Titan embeddings) via RAG wiring to ground agent responses in technical manuals.
Security and Compliance: Configure and wire Bedrock Guardrails for PII detection, prompt-injection defense, and content-moderation thresholds. Implement authentication using AWS Cognito, FastAPI JWT middleware, and custom Lambda authorizers.
Infrastructure & Deployment: Implement and manage serverless components (API Gateway, Python Lambda handlers) for service request creation and STREEM escalation triggers. Manage session state using DynamoDB and ElastiCache Redis.
Oferujemy:
Private medical care
Multisport card
Friendly, informal atmosphere, and direct contact with everyone in the company
Modern technologies
Availability to maintain partial overlap with the MT zone.
Min. 5 years of experience in Python engineering.
Practice in developing high-performance, resilient backend services and APIs (FastAPI).
Strong practical knowledge of AI/ML concepts, especially LLM orchestration, Retrieval-Augmented Generation (RAG), and prompt engineering.
Expertise in AWS services, including ECS/Fargate, Lambda, API Gateway, DynamoDB, ElastiCache, and Bedrock services (Nova 2 Sonic, Nova Micro).
Familiarity with the Strands Agents SDK or other multi-agent architecture frameworks.
Mile widziane:
BS/MS in Computer Science, Mathematics, Statistics, or a related quantitative field
O projekcie:
Acaisoft is a company partnering with industry leaders across healthcare, telecom, fintech, and insurance, building Cloud, Data & AI solutions for fast-moving businesses.
Although we are a Poland-based company, most of our clients are based in the U.S., so flexibility around non-standard working hours is important for smooth collaboration across time zones.
Currently, we are looking for a Senior AI/Backend Engineer to join the team developing the AI Voice Dispatch Assistant. This is a critical role focused on building a scalable, production-ready multi-agent voice AI solution, running entirely within the client's AWS perimeter.
Zakres obowiązków:
AI Agent Development: Design, implement, and maintain the multi-agent system using the Strands Agents SDK (BidiAgent) on ECS/Fargate, ensuring per-session isolation, auto-scaling, and managing the Nova 2 Sonic BidirectionalStream lifecycle.
Core Backend Services: Develop and maintain the production FastAPI backend, including a centralized AHS API client library (Member Service, Dispatch, Coverage / Eligibility) with features such as Pydantic models for complex responses, per-call audit logging with field-level PII masking, and per-endpoint caching.
LLM Orchestration & RAG: Implement the triage super-agent for first-turn domain routing (Nova Micro) and delegate to specialized sub-agents. Integrate Bedrock Knowledge Bases (OpenSearch Serverless, Titan embeddings) via RAG wiring to ground agent responses in technical manuals.
Security and Compliance: Configure and wire Bedrock Guardrails for PII detection, prompt-injection defense, and content-moderation thresholds. Implement authentication using AWS Cognito, FastAPI JWT middleware, and custom Lambda authorizers.
Infrastructure & Deployment: Implement and manage serverless components (API Gateway, Python Lambda handlers) for service request creation and STREEM escalation triggers. Manage session state using DynamoDB and ElastiCache Redis.
Oferujemy:
Private medical care
Multisport card
Friendly, informal atmosphere, and direct contact with everyone in the company
Modern technologies
🔍 Dekoder Ogłoszenia
🔴
Availability to maintain partial overlap with the MT zone.
Spodziewaj się pracy w niestandardowych godzinach, aby dopasować się do strefy czasowej klienta.
🔴
most of our clients are based in the U.S., so flexibility around non-standard working hours is important for smooth collaboration across time zones.
Praca będzie wymagała dostosowania się do godzin pracy klientów z USA, co może oznaczać wieczory lub wczesne poranki.
🟡
building a scalable, production-ready multi-agent voice AI solution, running entirely within the client's AWS perimeter.
Projekt jest ambitny i wymaga budowy złożonego systemu AI, który musi być stabilny i gotowy do produkcji w specyficznym środowisku klienta.
🔴
Familiarity with the Strands Agents SDK or other multi-agent architecture frameworks.
Możliwe, że będziesz musiał szybko nauczyć się specyficznego, być może niszowego, narzędzia lub frameworka.
🔴
Expertise in AWS services, including ECS/Fargate, Lambda, API Gateway, DynamoDB, ElastiCache, and Bedrock services (Nova 2 Sonic, Nova Micro).
Wymagana jest bardzo szeroka i głęboka znajomość konkretnych usług AWS, w tym tych mniej popularnych lub specyficznych dla klienta.