Job Description:

1. Key Highlights:

Participate in building AI workflow orchestration and automation platforms from scratch (0→1) or scaling existing ones (1→N), covering RAG, tool invocation, Agent collaboration, and asynchronous orchestration.
Implement Diffy or similar "shadow traffic replay + response diff comparison" solutions for model/version regression testing and gradual rollout.
Collaborate with multiple business lines (IM, customer service, marketing automation, data processing, etc.) to deliver real-world, production-grade closed-loop solutions.

Key Responsibilities:

2.1 AI/LLM Workflow Orchestration:

Design and implement multi-step reasoning, Agent collaboration, tool invocation (Tool-Calling/Function-Calling), asynchronous task queues, and compensation mechanisms.
Build and optimize RAG pipelines: data ingestion, chunking & vectorization, retrieval/reranking, context compression, caching, and cost reduction.

2.2 Evaluation & Quality Assurance:

Establish automated evaluation and alignment systems (benchmark sets, Ragas/G-Eval/custom metrics), integrating A/B testing and real-time monitoring.
Leverage Diffy (or equivalent) for shadow traffic replay and response diff analysis to identify regression risks in models/prompts/service upgrades; support canary releases and fast rollbacks.

2.3 Engineering & Observability:

Develop model/prompt versioning, feature/data versioning, experiment tracking (MLflow/W&B), and audit logs.
Implement end-to-end observability: latency, error rates, prompt/context length, hit rates, and cost monitoring (tokens/$).

2.4 Platform & Integration:

Expose workflows via API/SDK/microservices; integrate with business backends (Go/PHP/Node), queues (Kafka/RabbitMQ), storage (Postgres/Redis/object storage), and vector DBs (Milvus/Qdrant/pgvector).
Ensure security & compliance: anonymization, PII protection, auditing, rate limiting/quota, and model governance.

Job Requirements:

3. Must-Have Qualifications:

3+ years of backend or data/platform engineering experience, with 1–2+ years in LLM/generative AI projects.
Proficiency in LLM application engineering: prompt engineering, function/tool calling, dialogue state management, memory, structured output, alignment, and evaluation.
Hands-on experience with at least one orchestration framework: LangChain/LangGraph, LlamaIndex, Temporal/Prefect/Airflow, or custom DAG/state machine/compensation solutions.
End-to-end RAG expertise: data cleaning → vectorization → retrieval → reranking → evaluation; familiarity with Milvus/Qdrant/pgvector.
Experience with Diffy or equivalent traffic replay/diff comparison tools (shadow traffic, record/replay, regression output analysis, canary releases).
Strong engineering fundamentals: Docker, CI/CD, Git workflows, logging/metrics (OpenTelemetry/Prometheus/Grafana).
Proficiency in at least one primary language (Go/Python/TypeScript); ability to write reliable services and tests.
Excellent remote collaboration and documentation skills; data-driven delivery and retrospectives.

4. Preferred Qualifications:

Deep Diffy experience (or integrating shadow traffic/split testing with API gateways).
LLMOps/evaluation platform experience (Arize Phoenix, Evidently, PromptLayer, OpenAI Evals, Ragas).
Practical Agent framework implementations (LangGraph, autogen/crewAI, GraphRAG, tool ecosystems).
Security/compliance knowledge (anonymization, access control, PDPA/GDPR) and moderation tools (Llama Guard).
Familiarity with IM/customer service/marketing automation domains or multilingual scenarios (Chinese/English/Vietnamese).
Cost optimization skills: caching, retrieval compression, model routing/switching (OpenAI/Anthropic/Google/local models).

5. Tech Stack (Preferred):

Orchestration/Agent: LangChain/LangGraph, LlamaIndex, Temporal/Prefect/Airflow
Models & Evaluation: OpenAI/Anthropic/Google, VLLM/Ollama, Ragas, G-Eval, MLflow/W&B
Retrieval: Milvus, Qdrant, pgvector, Elasticsearch, rerankers (bge/multilingual/E5)
Services: Go/Python/TypeScript, gRPC/REST, Redis, Postgres, Kafka/RabbitMQ, Docker/K8s
Observability: OpenTelemetry, Prometheus, Grafana, ELK/ClickHouse
Diff/Replay: Twitter Diffy or equivalent shadow traffic/replay systems

Benefits:

Competitive salary
Career growth opportunities
Collaborative team environment
Fully remote work

🤖

AI Job Analysis

Intelligent Job Recommendations Based on Deep Learning

Ready for Analysis

Analyze Job Core Requirements

This Algorithm Engineer role at Deepcoin requires a blend of AI/LLM expertise, strong backend engineering skills, and experience with workflow orchestration platforms. The position focuses on building and scaling AI-driven solutions with a strong emphasis on RAG pipelines, Agent collaboration, and quality assurance.

3+ years of backend/data/platform engineering with 1–2+ years in LLM/generative AI projects
Proficiency in LLM application engineering (prompt engineering, tool calling, evaluation)
Hands-on experience with orchestration frameworks (LangChain, LlamaIndex, Temporal)
End-to-end RAG expertise (data cleaning → vectorization → retrieval → evaluation)
Strong engineering fundamentals (Docker, CI/CD, logging/metrics)

Understand Employer Recruitment Intent

Deepcoin appears to be scaling its AI infrastructure, particularly focusing on workflow automation and quality assurance in AI-driven applications. The emphasis on Diffy testing and shadow traffic replay suggests they prioritize stability and regression prevention in their AI services. Their requirement for multi-business line collaboration indicates these AI solutions will serve diverse internal functions (customer service, marketing automation, etc.). The preference for security/compliance knowledge hints at handling sensitive financial data, aligning with Deepcoin's likely position in the cryptocurrency/exchange sector.

MyJob Interviewer Says

As an interviewer for Deepcoin, I would prioritize candidates who demonstrate:
1) Practical experience implementing production-grade LLM solutions beyond just prototyping
2) Deep understanding of RAG optimization challenges (context compression, caching)
3) Evidence of implementing rigorous testing frameworks (Diffy, shadow traffic)
4) Ability to articulate trade-offs between different orchestration approaches
5) Experience working in regulated environments would be a significant plus

AI Matching Suggestions

To optimize your application for Deepcoin's Algorithm Engineer position:

Highlight specific RAG implementations you've built, emphasizing optimization techniques used
Detail your experience with shadow traffic/testing frameworks like Diffy
Showcase contributions to AI workflow orchestration platforms (0→1 or scaling)
Demonstrate security/compliance awareness relevant to financial/crypto applications
Prepare concrete examples of cost optimization in LLM deployments
Be ready to discuss multi-agent collaboration implementations

Algorithm Engineer at Deepcoin

Employment Information

Job Description:

Key Responsibilities:

Job Requirements:

Benefits:

AI Job Analysis

Analyze Job Core Requirements

Understand Employer Recruitment Intent

MyJob Interviewer Says

AI Matching Suggestions

Test Engineer

$2,500 - $4,500 /hour

Golang Engineer

$3,000 - $5,500 /hour

Customer Service

$1,800 - $2,100 /hour

Product Manager

$3,500 - $5,500 /hour

Flutter Engineer

$4,000 - $5,500 /hour

Language & Currency

Language

Currency

Algorithm Engineer at Deepcoin

Employment Information

Job Description:

Key Responsibilities:

Job Requirements:

Benefits:

$2,500 - $4,500 /hour

$3,000 - $5,500 /hour

$1,800 - $2,100 /hour

$3,500 - $5,500 /hour

$4,000 - $5,500 /hour

New Things Will Always Update Regularly

New Things Will Always
Update Regularly